Vehicle climate control system with clothing level compensation

Abstract

A climate control system includes a memory, a compensation module, and a climate control module. The memory is configured to store images captured by one or more image sensors. The compensation module is configured to: estimate a clothing level of a first occupant in an interior cabin of a vehicle based on the images or receive the clothing level from at least one of an edge computing device or a cloud-based network device; determine a first EHT setpoint; and determine a first composite EHT based on the clothing level and the first EHT setpoint. The climate control module is configured to: determine a first EHT error based on the first composite EHT and a cabin temperature setpoint; determine a control value based on the first EHT error; and set climate control parameters to control the temperature of a first zone within the interior cabin based on the control value.

Description

Background Art

[0001] The information provided in this section is for the purpose of generally presenting the background of the present disclosure. To the extent described in this section, the work of the presently named inventors and aspects of the description that may not be prior art on the filing date are neither explicitly nor implicitly admitted to be prior art to the present disclosure.

[0002] The present disclosure relates to vehicle climate control systems.

[0003] Motor vehicles include a heating, ventilation, and air conditioning (HVAC) system for controlling the temperature within the vehicle's interior cabin. The HVAC system provides thermal comfort for vehicle occupants by maintaining a target temperature that can be set by the occupants. Different temperatures can be set for different zones within the vehicle's interior cabin. The temperature can be controlled based on signals from temperature sensors in the corresponding zones. Summary of the Invention

[0004] A climate control system is provided and includes a memory, a compensation module, and a climate control module. The memory is configured to store images captured by one or more image sensors. The compensation module is configured to: estimate a clothing level of a first occupant in an interior cabin of a vehicle based on the images or receive the clothing level from at least one of an edge computing device or a cloud-based network device; determine a first equivalent homogeneous temperature (EHT) setpoint; and determine a first composite EHT based on the clothing level and the first EHT setpoint. The climate control module is configured to: determine a first composite EHT error based on the first composite EHT and a cabin temperature setpoint; determine a control value based on the first EHT error; and set climate control parameters to control the temperature of a first zone within the interior cabin based on the control value.

[0005] In other features, the climate control system further includes the one or more image sensors.

[0006] In other features, the climate control system further includes a transceiver configured to transmit the image to the edge computing device and receive the clothing level from the edge computing device.

[0007] In other features, the climate control system further includes an edge computing device, wherein the edge computing device includes a convolutional neural network configured to analyze the image and estimate a degree of clothing of the first occupant based on analysis results provided by the convolutional neural network.

[0008] In other features, the climate control system further includes a transceiver configured to transmit the image to the cloud-based network device and receive the clothing level from the cloud-based network device.

[0009] In other features, the compensation module is configured to: calculate an EHT compensation value based on the skin temperature and a baseline EHT temperature at a baseline clothing level; and determine a first resultant EHT based on the EHT compensation value.

[0010] In other features, the compensation module is configured to: estimate a clothing level of a second occupant in the interior cabin of the vehicle based on the image or receive the clothing level of the second occupant from at least one of the edge computing device or the cloud-based network device; determine a second EHT setpoint; and determine a second resultant EHT based on the clothing level of the second occupant and the second EHT setpoint. The climate control module is configured to: determine a second EHT error based on the second resultant EHT and a second cabin temperature setpoint for a second zone; determine another control value based on the second EHT error; and set climate control parameters to control the temperature of the second zone within the interior cabin based on the another control value.

[0011] In other features, the climate control system further includes a transceiver configured to transmit the image to the edge computing device and receive a clothing level of the second occupant from the edge computing device.

[0012] In other features, the climate control system further includes a transceiver configured to transmit the image to the cloud-based network device and receive the clothing level of the second occupant from the cloud-based network device.

[0013] In other features, the climate control module is configured to set the climate control parameter to adjust an opacity level of at least one of a sunroof or one or more vehicle windows.

[0014] In other features, a climate control method is provided and includes: capturing and storing images in a memory by one or more image sensors; estimating a clothing level of a first occupant in an interior cabin of a vehicle based on the images or receiving the clothing level from at least one of an edge computing device or a cloud-based network device; determining a first equivalent homogeneous temperature (EHT) set point; determining a first composite EHT based on the clothing level and the first EHT set point; determining a first EHT error based on the first composite EHT and a cabin temperature set point; determining a control value based on the first EHT error; and setting climate control parameters to control the temperature of a first area within the interior cabin based on the control value.

[0015] In other features, the climate control method further includes transmitting the image to the edge computing device and receiving the clothing level from the edge computing device.

[0016] In other features, the climate control method further includes analyzing the image via a convolutional neural network and estimating the clothing level of the first occupant based on analysis results provided by the convolutional neural network.

[0017] In other features, the climate control method further comprises transmitting the image to the cloud-based network device and receiving the clothing level from the cloud-based network device.

[0018] In other features, the climate control method further includes analyzing the image via a convolutional neural network and estimating the clothing level of the first occupant based on analysis results provided by the convolutional neural network.

[0019] In other features, the climate control method further comprises calculating an EHT compensation value based on skin temperature and a baseline EHT temperature at a baseline clothing level; and determining the first resultant EHT based on the EHT compensation value.

[0020] In other features, the climate control method further includes: estimating a clothing level of a second occupant in the interior cabin of the vehicle based on the image or receiving the clothing level of the second occupant from at least one of the edge computing device or the cloud-based network device; determining a second EHT set point; determining a second composite EHT based on the clothing level of the second occupant and the second EHT set point; determining a second EHT error based on the second composite EHT and a second cabin temperature set point for a second area; determining another control value based on the second EHT error; and setting climate control parameters to control the temperature of the second area within the interior cabin based on the another control value.

[0021] In other features, the climate control method further includes transmitting the image to the edge computing device and receiving the clothing level of the second occupant from the edge computing device.

[0022] In other features, the climate control method further includes transmitting the image to the cloud-based network device and receiving the clothing level of the second occupant from the cloud-based network device.

[0023] In other features, the climate control method further includes setting the climate control parameter to adjust an opacity level of at least one of a sunroof or one or more vehicle windows.

[0024] The present invention also includes the following solutions:

[0025] Solution 1. A climate control system comprising:

[0026] a memory configured to store images acquired by the one or more image sensors;

[0027] The compensation module is constructed as

[0028] estimating a clothing level of a first occupant in an interior cabin of the vehicle based on the image or receiving the clothing level from at least one of an edge computing device or a cloud-based network device;

[0029] determining a first equivalent homogenization temperature (EHT) set point; and

[0030] determining a first resultant EHT based on the clothing level and the first EHT set point; and

[0031] A climate control module is configured to

[0032] determining a first EHT error based on the first composite EHT and a cabin temperature set point;

[0033] determining a control value based on the first EHT error; and

[0034] A climate control parameter is set to control a temperature of a first area within the interior cabin based on the control value.

[0035] Option 2. The climate control system according to Option 1, further comprising the one or more image sensors.

[0036] Option 3. The climate control system of Option 1 further comprises a transceiver configured to transmit the image to the edge computing device and receive the clothing level from the edge computing device.

[0037] Option 4. The climate control system according to Option 3 further includes the edge computing device, wherein the edge computing device includes a convolutional neural network, and the convolutional neural network is configured to analyze the image and estimate the clothing level of the first occupant based on the analysis results provided by the convolutional neural network.

[0038] Embodiment 5. The climate control system of embodiment 1 further comprises a transceiver configured to transmit the image to the cloud-based network device and receive the clothing level from the cloud-based network device.

[0039] Embodiment 6. The climate control system of embodiment 1, wherein the compensation module is configured to:

[0040] calculating an EHT compensation value based on skin temperature and a baseline EHT temperature at a baseline clothing level; and

[0041] The first synthetic EHT is determined based on the EHT compensation value.

[0042] Option 7. The climate control system of Option 1, wherein:

[0043] The compensation module is configured as

[0044] estimating a clothing level of a second occupant in the interior cabin of the vehicle based on the image or receiving the clothing level of the second occupant from the at least one of the edge computing device or the cloud-based network device;

[0045] determining a second EHT set point; and

[0046] determining a second resultant EHT based on the clothing level of the second occupant and the second EHT setpoint; and

[0047] The climate control module is configured to

[0048] determining a second EHT error based on the second synthetic EHT and a second cabin temperature set point for a second zone;

[0049] determining another control value based on the second EHT error; and

[0050] A climate control parameter is set to control the temperature of the second area within the interior cabin based on the other control value.

[0051] Option 8. The climate control system of Option 7, further comprising a transceiver configured to transmit the image to the edge computing device and receive the clothing level of the second occupant from the edge computing device.

[0052] Embodiment 9. The climate control system of embodiment 7, further comprising a transceiver configured to transmit the image to the cloud-based network device and receive the clothing level of the second occupant from the cloud-based network device.

[0053] Embodiment 10. The climate control system of embodiment 1, wherein the climate control module is configured to set the climate control parameter to adjust an opacity level of at least one of a sunroof or one or more vehicle windows.

[0054] A method for climate control comprising:

[0055] capturing images by one or more image sensors and storing them in a memory;

[0056] estimating a clothing level of a first occupant in an interior cabin of the vehicle based on the image or receiving the clothing level from at least one of an edge computing device or a cloud-based network device;

[0057] determining a first equivalent homogenization temperature (EHT) set point;

[0058] determining a first resultant EHT based on the clothing level and the first EHT set point;

[0059] determining a first EHT error based on the first composite EHT and a cabin temperature set point;

[0060] determining a control value based on the first EHT error; and

[0061] A climate control parameter is set to control a temperature of a first area within the interior cabin based on the control value.

[0062] Option 12. The climate control method according to Option 11 further includes transmitting the image to the edge computing device and receiving the clothing level from the edge computing device.

[0063] Option 13. The climate control method according to Option 12 further includes analyzing the image via a convolutional neural network, and estimating the clothing level of the first occupant based on the analysis results provided by the convolutional neural network.

[0064] Embodiment 14. The climate control method of embodiment 11 further comprises transmitting the image to the cloud-based network device and receiving the clothing level from the cloud-based network device.

[0065] Option 15. The climate control method according to Option 14 further includes analyzing the image via a convolutional neural network, and estimating the clothing level of the first occupant based on the analysis results provided by the convolutional neural network.

[0066] Option 16. The climate control method according to Option 11, further comprising:

[0067] calculating an EHT compensation value based on skin temperature and a baseline EHT temperature at a baseline clothing level; and

[0068] The first synthetic EHT is determined based on the EHT compensation value.

[0069] Option 17. The climate control method according to Option 11, further comprising:

[0070] estimating a clothing level of a second occupant in the interior cabin of the vehicle based on the image or receiving the clothing level of the second occupant from the at least one of the edge computing device or the cloud-based network device;

[0071] determining a second EHT set point;

[0072] determining a second resultant EHT based on the clothing level of the second occupant and the second EHT setpoint; and

[0073] determining a second EHT error based on the second composite EHT and a second cabin temperature set point for a second zone;

[0074] determining another control value based on the second EHT error; and

[0075] A climate control parameter is set to control the temperature of the second area within the interior cabin based on the other control value.

[0076] Option 18. The climate control method according to Option 17 further includes transmitting the image to the edge computing device and receiving the clothing level of the second occupant from the edge computing device.

[0077] Embodiment 19. The climate control method of embodiment 17 further comprises transmitting the image to the cloud-based network device and receiving the clothing level of the second occupant from the cloud-based network device.

[0078] Embodiment 20. The climate control method of embodiment 11, further comprising setting the climate control parameter to adjust the opacity of at least one of a sunroof or one or more vehicle windows.

[0079] Further areas of applicability of the present disclosure will become apparent from the detailed description, claims and accompanying drawings.The detailed description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] The present disclosure will be more fully understood from the detailed description and accompanying drawings, in which:

[0081] Figure 1 is a functional block diagram of an example of an EHT-based climate control system that performs exterior clothing detection of vehicle occupants according to the present disclosure;

[0082] Figure 2 yes Figure 1 A functional block diagram of a portion of an EHT-based climate control system;

[0083] Figure 3is a perspective view of a portion of a vehicle illustrating image capture of a vehicle occupant for clothing level estimation;

[0084] Figure 4 is a perspective view of a portion of a vehicle illustrating image capture of a plurality of vehicle occupants for clothing level estimation;

[0085] Figure 5 The following is an example graph showing the relationship between the predicted mean vote (PMV) index and the EHT for different levels of clothing without compensation based on the level of clothing;

[0086] Figure 6 is an example graph including a plot of the PMV index versus EHT for different clothing levels with compensation based on clothing level according to the present disclosure;

[0087] Figure 7 An exemplary EHT-based climate control system with clothing level compensation according to the present disclosure is shown;

[0088] Figure 8A-8B An exemplary EHT-based climate control method implemented by a vehicle according to the present disclosure is shown; and

[0089] Figure 9 An exemplary clothing level estimation method implemented by an edge computing and / or cloud-based network device according to the present disclosure is shown.

[0090] In the drawings, reference numerals may be repeated to refer to similar and / or identical elements. DETAILED DESCRIPTION

[0091] Various heat sources can affect the temperature within a vehicle's interior cabin and, therefore, the comfort of the occupants within. These sources can include the engine, vehicle windows, one or more heaters, solar energy (referred to herein as solar load), external heat from the outside air, structural elements (e.g., panels and seats), occupants, and / or other heat sources mentioned below. The extent of the outside air's heat energy depends on the air temperature (or external ambient temperature). For example, a vehicle's windshield and instrument panel can experience high surface temperatures. Furthermore, temperature can be affected by varying air velocity, vehicle speed, and HVAC blower speed. The temperature of each component within the interior cabin can be related to and / or dependent on the temperature of other components within the interior cabin and / or other environmental conditions. Consequently, the temperature distribution and relationships within the interior cabin are complex and difficult to characterize and define. This makes it challenging to calibrate the HVAC control system for occupant thermal comfort.

[0092] The example described in this article simplifies the calibration process while providing improved occupant thermal comfort. The example eliminates subjective dependencies and individual calibrator variations in the conventional automatic climate control (ACC) calibration process.

[0093] Examples include a vehicle climate control system that accounts for various occupant clothing levels based on captured images obtained via image sensors (e.g., cameras and infrared sensors). Machine learning algorithms and neural networks are used to detect the clothing levels of one or more occupants in one or more zones of the vehicle cabin. One or more equivalent homogeneous temperature (EHT) values ​​for the zones are then adjusted to account for the clothing levels. Various actuators are then controlled based on the adjusted EHT values ​​to provide thermal comfort to the one or more occupants.

[0094] Figure 1 An EHT-based climate control system 100 is shown that implements exterior clothing detection of occupants within a vehicle 102. The EHT-based climate control system 100 includes the vehicle 102 and may include an edge computing device 104 and / or a cloud-based network device 106, which can communicate with each other via a distributed network 108. The edge computing device 104 can be located inside or outside the vehicle 102, as shown. The edge computing device 104 can be an infrastructure device that utilizes vehicle-to-infrastructure (V2I) communication and is located, for example, along a roadway along which the vehicle 102 is traveling. The infrastructure device can include traffic signals, traffic signs, building-mounted devices, and / or roadway structures, among others. The edge computing device 104 can be a micro-data center deployed at a cellular tower and / or regional station. The cloud-based network device can be remotely located at a central location and controlled, for example, by a service provider.

[0095] The vehicle 102, edge computing device 104, and cloud-based network device 106 may include corresponding transceivers 110, 112, 114, control modules 116, 118, 120, and memories 122, 124, 126. The vehicle control module 116 may include an EHT compensation module 130 and a climate control module 132. The control module 118 (or edge node control module) may include a clothing level module 140. The server control module 120 (or server control module) may include another clothing level module 150.

[0096] Clothing level modules 140 and 150 receive interior cabin images captured within vehicle 102 and estimate the clothing level of occupants within vehicle 102 based on the images. Clothing level modules 140 and 150 may each include a neural network and implement a machine learning algorithm to estimate clothing level. The neural network may include a convolutional neural network. The machine learning algorithm may operate to better detect the presence of clothing, the degree of clothing, and identify different types of clothing, such as pants, shirts, shorts, jackets, hats, gloves, etc. In one embodiment, edge node control module 118 performs real-time data processing on the image data received from vehicle 102 to perform basic analysis and communicates the analysis results to server control module 120 for further analysis. The neural network detects feature lines and other attributes of objects shown in the image. EHT compensation module 130 adjusts the EHT value based on the estimated clothing level. Climate control module 132 controls the temperature within the vehicle cabin based on the adjusted EHT value. These operations are further described below.

[0097] Figure 2 Shown is a vehicle 102 Figure 1 Portion 200 of the EHT-based climate control system 100 is shown. The vehicle 102 may be a partially or fully autonomous vehicle or another type of vehicle. Portion 200 includes the vehicle control module 116, memory 122, sensors 202, and an HVAC system 204. The vehicle control module 116 includes modules 130 and 132 and may include other modules 206. The climate control module 132 controls the temperature within the cabin of the vehicle 102 based on one or more compensated EHT values ​​and one or more target (or set) temperatures for corresponding zones. Each zone may have a corresponding compensated EHT value and / or target temperature. Two or more zones may share a single compensated EHT value and / or target temperature. The target temperature may be set based on input received from a vehicle occupant via temperature input controls 208. Temperature input controls 208 may include knobs, buttons, sliders, touchscreen icons, and the like, and may be located on an instrument panel, a center console, an overhead console, and / or other locations. The target temperature may be set via voice command using a speaker, a portable network device (eg, a mobile phone, tablet, wearable device, etc.), and / or via some other input device.

[0098] To adjust the temperature within the vehicle cabin to match the target temperature, the climate control module 132 can control the HVAC system 204 and other temperature-regulating components, devices, and systems. This can include controlling the temperature and velocity of air discharged into and / or circulated around the vehicle cabin. The climate control module 132 can control the speed of one or more blowers (or fans) 210. In one embodiment, the vehicle 102 includes smart glass 212. As an example, a sunroof of the vehicle 102 can include smart glass 212. The climate control module 132 can control the opacity of the smart glass 212 based on the compensated EHT value and the target temperature.

[0099] Memory 122 may store EHT values ​​211 (e.g., EHT setpoints, EHT compensation values, EHT errors, etc.), other parameters 213, data 214, and algorithms 216 (e.g., EHT compensation algorithms, machine learning algorithms, etc.). Sensors 202 may be located throughout vehicle 102 and include cameras 220, infrared (IR) sensors 222, external ambient temperature sensors 224, one or more interior cabin temperature sensors 226, and / or other sensors 228. An interior cabin temperature sensor may be included for each zone of the interior cabin of vehicle 102. Other sensors 228 may include a yaw rate sensor, an accelerometer, a global positioning system (GPS) sensor, an air flow sensor, a temperature sensor, a pressure sensor, a vehicle speed sensor, a motor speed sensor, and the like. Vehicle control module 116 and sensors 202 may communicate directly with each other, via a controller area network (CAN) bus 230, and / or via an Ethernet switch 232. In the example shown, the sensor 202 is connected to the vehicle control module 116 via an Ethernet switch 232 , but may also or alternatively be connected directly to the vehicle control module 116 and / or the CAN bus 230 .

[0100] The vehicle 102 may further include other control modules, such as a chassis control module 240, which controls torque sources including one or more electric motors 242 and one or more engines (one engine 244 is shown). The chassis control module 240 may control the distribution of output torque via the torque sources to the axles of the vehicle 102. The chassis control module 240 may control the operation of a propulsion system 246 including the electric motor(s) 242 and the engine(s) 244. Each engine may include a starter motor 250, a fuel system 252, an ignition system 254, and a throttle system 256.

[0101] In one embodiment, the vehicle control module 116 is a body control module (BCM) that communicates with and / or controls the operation of the telematics module 262, the braking system 263, the navigation system 264, the infotainment system 266, other actuators 272 and devices 274, and other vehicle systems and modules 276. The navigation system 264 may include a GPS 278. The other actuators 272 may include a steering actuator and / or other actuators. The modules and systems 116, 204, 240, 262, 264, 266 may communicate with each other via a CAN bus 230. A power supply 280 may be included and provide power to the vehicle control module 116 and other systems, modules, controllers, memories, devices, and / or components. The power supply 280 may include one or more batteries and / or other power sources. The control module 116 may execute countermeasures and / or autonomous vehicle operations based on the planned trajectory of the vehicle 102, detected objects, the locations of the detected objects, and / or other relevant operations and / or parameters. This may include controlling the noted torque sources and actuators as well as providing images, indications, and / or commands via the infotainment system 266 .

[0102] The telematics module 262 may include a transceiver 282 and a telematics control module 284, which may be used to communicate with other vehicles, networks, edge computing devices, and / or cloud-based devices. The transceiver 282 may include Figure 1 The control module 116 can control the modules and systems 204, 262, 263, 264, 266 and other actuators, devices and systems (e.g., smart glass 212, actuator 272 and device 274). This control can be based on data from the sensor 202.

[0103] Figure 3 Showing a vehicle (e.g. Figure 1-Figure 2 A portion 300 of a vehicle 102 is shown, illustrating image capture of a vehicle occupant 302 for clothing level estimation. In the illustrated example, a single image sensor 304 is used to capture an image of the vehicle occupant 302 within the vehicle's interior cabin 303. Image sensor 304 may be a camera or an IR sensor. The image captured by image sensor 304 may then be analyzed as described herein to estimate the clothing level of occupant 302. While a single image sensor is shown, any number of image sensors may be included to capture images of occupant 302 and / or other occupants within the vehicle. Arrow 306 represents vehicle speed, which may be monitored when detecting parameters that may affect interior cabin temperature.

[0104] Reference numeral 308 indicates the smart glass of the vehicle. In the example shown, the vehicle includes a sunroof that includes smart glass that can be controlled by the occupant 302 based on their clothing. Figure 1-Figure 2 The vehicle control module 116 controls the smart glass. The vehicle may include a radiant heater and / or element 310 that may be controlled by the vehicle control module 116 to adjust the temperature within the interior cabin. The vehicle control module 116 may further control Figure 2 The HVAC system 204 and the blower 210 are used to adjust the exhaust Figure 3 The air flow temperature T of the air in the interior cabin 303 and / or circulating in the interior cabin air and speed V air .

[0105] Figure 4 A vehicle (e.g., Figure 1-Figure 2 A portion 400 of a vehicle 102 is shown, illustrating image capture of multiple occupants 402 for clothing level estimation. In the illustrated example, a single image sensor 404 is used to capture images of vehicle occupants 402 within the vehicle's interior cabin 403. Image sensor 404 may be a camera or an IR sensor. The images captured by image sensor 404 may then be analyzed as described herein to estimate the clothing levels of occupants 402. While a single image sensor is shown, any number of image sensors may be included to capture images of occupants 402.

[0106] Figure 5 A graph is shown that plots the predicted mean vote (PMV) index versus EHT for different levels of clothing without compensation based on clothing level. In the example shown, multiple groups of points are plotted for four different levels of clothing (Iclo = 0.3, Iclo = 0.6, Iclo = 1.0, and Iclo = 1.2). Linear curves 500, 502, 504, and 506 are provided for each of these four different levels of clothing, respectively, and are fitted to the groups of points. A clothing level of Iclo = 0 indicates that the occupant is wearing no clothing. A clothing level of Iclo = 0.6 indicates that the occupant is wearing light clothing (e.g., warm summer clothing such as a shirt and T-shirt). A clothing level of Iclo = 1.2 indicates that the occupant is wearing heavy clothing (e.g., cold winter clothing such as pants, a winter coat, a hat, and gloves). The PMV is an empirical fit to the human perception of thermal comfort. A PMV of 5 is considered warm. A PMV of 0 is considered neutral. A PMV of -5 is considered cold. The unit of measurement for EHT is °C (Celsius). As can be seen from the plot, the greater the degree of clothing, the smaller the temperature difference or temperature change that the occupant experiences.

[0107] Figure 6A graph is shown that includes a plot of the PMV index versus EHT for different clothing levels with clothing level-based compensation as disclosed herein. In the example shown, groups of points are plotted for four different clothing levels (Iclo = 0.3, Iclo = 0.6, Iclo = 1.0, and Iclo = 1.2). As can be seen, the groups of points can be generally curve-fitted to the same linear curve 600. Thus, the temperature compensation disclosed herein accounts for different clothing levels and minimizes the temperature changes experienced and / or perceived by vehicle occupants.

[0108] Figure 7 An exemplary EHT-based climate control system 700 with clothing level compensation is shown. The EHT-based climate control system 700 may be comprised of Figure 1-Figure 2 The vehicle control module 116 is implemented as shown in FIG. Based on the EHT, the climate control system 700 can set an EHT setpoint (EHTsp), as represented by block 702. The EHT setpoint (EHTsp) can be determined using conventional methods. A lookup table can be used to determine the EHT setpoint (EHTsp) based on the application and various parameters. The application can refer to the type of vehicle and vehicle characteristics, such as the size of the cabin, the materials in the cabin, the number and size of the windows, the degree of opacity of the windows, the type of heater and heating element, the number of seats, the materials in the cabin, the number of occupants, and the like. The EHT setpoint (EHTsp) can be a fixed value or can be adjusted based on these and other factors.

[0109] The EHT set point EHTsp can be set at, for example, 24°C, which can correspond to a comfort level of 5 on a comfort scale of 1-9. On the example comfort scale, 1 can be classified as cold, 2 can be classified as very cool, 3 can be classified as cool, 4 can be classified as slightly cool, 5 can be classified as comfortable, 6 can be classified as slightly warm, 7 can be classified as warm, 8 can be classified as too warm, and 9 can be classified as hot. Depending on the individual, the season, and the degree of clothing, an occupant can be "comfortable" at an EHT set point EHTsp within the range of 20-25°C.

[0110] The EHT set point EHTsp may be provided to a first adder 704, which adds EHTsp to the EHT compensation value ∆T Iclo-EHT The EHT compensation value ∆T can be calculated based on the estimated clothing level Iclo Iclo-EHT , as represented by block 712. The clothing level Iclo may be determined by the vehicle control module 116, by another module in the vehicle, or externally at an edge computing device (e.g., Figure 1 edge computing device 104) or by a cloud-based network device (e.g., Figure 1 The cloud-based network device 106) estimates.

[0111] The first summer provides a synthesized EHT value EHTres, which can be provided to a second summer 706. The synthesized EHT value EHTres is independent of the external ambient temperature Ta, the solar load level, the HVAC air velocity of the air discharged into and circulated within the vehicle's interior cabin, and the interior cabin temperature. The EHT for neutral thermal perception depends on the occupant's metabolic rate and clothing level. The calculation of the synthesized EHT value EHTres takes clothing level into account. The synthesized EHT value referred to herein is used to provide a representative value for characterizing a non-uniform thermal environment as a uniform thermal environment relevant to occupant thermal perception.

[0112] The second adder may subtract the temperature set point Tsp from the synthesized EHT value EHTres to provide an EHT error value ∆EHT. The temperature set point Tsp may be determined based on a control signal CONT (716), an external ambient temperature Ta (718), a solar load level (720), an HVAC air velocity (722) of air being discharged into or circulated within the interior cabin of the vehicle, an interior cabin temperature 724 (e.g., an interior cabin temperature Tc and / or other interior cabin temperatures), and / or other parameters. The temperature set point Tsp may be set based on a radiant average temperature in the interior cabin of the vehicle. The temperature set point Tsp may be based on steady-state values ​​of these parameters and / or transients (or changes) of these parameters. This operation is represented by block 714. A control signal 716 may be generated, for example, based on a vehicle occupant input indicating a set temperature requested by a vehicle occupant. This may be generated, for example, by Figure 2 The temperature input is provided to one of the control devices 208.

[0113] Block 708 represents determining a control value Yn based on the EHT error value ∆EHT and one or more of the signals 718, 720, 722, and 724. The control value Yn may be based on steady-state values ​​of these parameters and / or transient states (or changes) of these parameters. A proportional-integral-derivative (PID) controller may be used to generate the control value Yn using feedback control.

[0114] Block 710 represents determining climate control parameters based on the control value Yn, where the climate control parameters include window (or smart glass) opacity, blower speed, exhaust or recirculated air temperature Tair, HVAC mode, radiant heater and / or heating element radiant heating settings, etc. The HVAC mode may include a heating mode, a cooling mode, an air recirculation mode, an air exhaust mode, or a combination thereof.

[0115] Can be executed simultaneously Figures 8A-9 The following method can be executed according to Figure 8A-8B method, Figure 8A-8B Shown by Figure 1-Figure 2The method may be performed iteratively. The method may begin at 800. At 802, the sensor 202 captures images of one or more areas of the interior of the vehicle 102.

[0116] At 804, the EHT compensation module 130 may determine whether to send the captured image to an external processing device (eg, Figure 1 If yes, then operation 806 is performed, otherwise operation 810 is performed.

[0117] At 806 , the EHT compensation module 130 transmits the image to an external processing device.

[0118] At 808 , the EHT compensation module 130 receives one or more clothing levels of one or more occupants in the one or more regions from an external processing device. A signal identifying the occupant, the occupant's location, and the occupant's clothing level may be received from the external processing device.

[0119] At 810, the EHT compensation module 130 may analyze the captured image to detect the occupant, the occupant's position, and the occupant's clothing. At 812, the EHT compensation module 130 detects the occupant and the occupant's position. This may include object, size, and shape image recognition based on historical data. The EHT compensation module 130 may use neural networks to perform image processing to recognize shapes, colors, object detection, skin recognition, clothing patterns, etc. The presence of an occupant may also be detected via non-image-based signals. For example, weight and / or strain sensors in the vehicle's seat may indicate that an occupant is on the vehicle's seat.

[0120] At 814, the EHT compensation module 130 may determine the degree of clothing of the occupant. This may include using a neural network and / or a machine learning system to perform object, size, and shape image recognition based on historical data. The EHT compensation module 130 may use a neural network to perform image processing to recognize shapes, colors, object detection, skin recognition, clothing patterns, etc. The pixels of the image may be analyzed for various known patterns to identify the identifying features and / or other features, such as clothing type.

[0121] At 816 , the EHT compensation module 130 calculates an EHT compensation value ∆T based on the clothing level. Iclo-EHT As an example, the EHT compensation value ∆T Iclo-EHT It can be determined by using Equation 1-Equation 2, where Iclo0 is the baseline clothing level (e.g., 0.6), Iclo is the determined clothing level, and T skin is the human skin temperature (e.g., 34°C), and T EHT0is the reference EHT for baseline clothing level Iclo0. Baseline clothing level Iclo0 and skin temperature T skin Can be a fixed value. Equation 2 can be used to first determine T EHT0 And then Equation 1 can be used to determine the EHT compensation value ∆T Iclo-EHT EHT compensation value ∆T Iclo-EHT Can be positive or negative.

[0122] (1)

[0123] T EHT0 =In Iclo 0 Baseline T at EHT0 (2)

[0124] Although Equation 1 includes a ratio having a constant scale value of 1.395 in the numerator and denominator, other constant values ​​may be used.

[0125] At 818 , the EHT compensation module 130 calculates the EHT compensation value ∆T based on the EHT set point EHTsp and the EHT compensation value ∆T Iclo-EHT The composite EHT value EHTres is determined. The composite EHT value EHTres can be the EHT set point EHTsp and the EHT compensation value ∆T Iclo-EHT At 820, the climate control module 132 determines the outside ambient air temperature, cabin temperature, solar load, and HVAC air discharge rate. At 821, the climate control module 132 determines the cabin temperature set point Tsp. This can be as described in reference Figure 7 The block 714 is completed as described above. Operation 822 may be performed after operations 818 and 821.

[0126] At 822 , the climate control module 132 may determine an EHT error value ∆EHT based on the combined EHT value EHTres and the set point temperature Tsp. This may be done via Figure 7 The adder 706 is implemented as follows. At 824, the climate control module 132 may determine a control value Yn based on the EHT error value ∆EHT. This may be accomplished by using one or more tables and / or one or more equations that correlate EHT error values ​​to values ​​Yn. At 826, the climate control module 132 determines a climate control parameter based on the control value Yn. This may be accomplished by using one or more tables and / or one or more equations that correlate values ​​Yn to climate control parameters. At 828, the climate control module 132 controls the HVAC system 204 based on the climate control parameter.

[0127] At 830 , the climate control module 132 determines whether there is another zone for which to perform the above operations and / or whether another iteration of the above operations should be performed for the same one or more zones. If so, operation 802 may be performed, otherwise the method may end at 832 .

[0128] Figure 9 edge computing and / or cloud-based network devices (e.g. Figure 1 The method for estimating the degree of clothing implemented by the device 104, 106) can be performed iteratively and can be performed by Figure 1 The method may begin at 900. At 902, the control module receives an acquired image from the vehicle 102.

[0129] At 904, the control module may analyze the captured image to detect the occupants, their positions, and the occupants' clothing levels. At 906, the control module detects the occupants and their positions. This may include object, size, and shape image recognition based on historical data. The control module may use a neural network to perform image processing to identify shapes, colors, object detection, skin recognition, clothing patterns, and the like. At 908, the control module may determine the occupants' clothing levels. This may include using a neural network and / or a machine learning system to perform image processing to identify shapes, colors, object detection, skin recognition, clothing patterns, and the like. The pixels of the image may be analyzed for various known patterns to identify the identifying features and / or other features, such as clothing type.

[0130] At 910, the control module transmits a signal to the vehicle 102 indicating the one or more determined clothing levels. The signal may also indicate the detection and location of one or more corresponding occupants. At 912, the control module may determine whether to perform the above method for another area of ​​the interior cabin of the vehicle 102. If so, operation 902 may be performed; otherwise, the method may end at 914.

[0131] The above example includes a climate control system that personalizes thermal comfort based on an individual's clothing level. Clothing level can be determined using a convolutional neural network. The example provides thermal comfort by controlling the temperature within a vehicle's interior cabin while minimizing human subjectivity in temperature calibration. Actuators can be controlled based on automatically determined control parameters without and / or independent of occupant intervention. Thermal comfort can also be provided while minimizing energy consumption of the HVAC system. Local temperatures are determined for different occupants within a region within the vehicle to provide customized thermal comfort for each occupant.

[0132] The system uses EHT values ​​to convert a non-uniform environment into a uniform representation. The EHT-based climate control system described herein provides vehicle occupants with real-time control of smart glass, radiant heating, exhaust air temperature, blower speed, and HVAC modes to create a neutral thermal sensation (not too hot, not too cold). The system also provides fine-tuning of the control setpoint temperature based on the occupant's clothing level.

[0133] The above description is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or use. The broad teachings of the present disclosure can be implemented in various forms. Therefore, although the present disclosure includes specific examples, the true scope of the present disclosure should not be limited thereto, because other modifications will become apparent upon studying the drawings, the specification, and the appended claims. It should be understood that one or more steps in the method can be performed in a different order (or simultaneously) without changing the principles of the present disclosure. Further, although each embodiment is described above as having certain features, any one or more of these features described with respect to any embodiment of the present disclosure can be implemented in the features of any of the other embodiments and / or combined with the features of any of the other embodiments, even if such a combination is not explicitly described. In other words, the embodiments are not mutually exclusive, and the permutation of one or more embodiments with each other falls within the scope of the present disclosure.

[0134] Various terms are used to describe spatial and functional relationships between elements (e.g., between modules, circuit elements, semiconductor layers, etc.) including "connected," "engaged," "coupled," "adjacent," "next to," "on top of," "above," "below," and "disposed." Unless explicitly described as "directly," when describing a relationship between a first and a second element in the above disclosure, the relationship can be a direct relationship with no other intervening elements between the first and second elements, but can also be an indirect relationship with one or more intervening elements (spatially or functionally) between the first and second elements. As used herein, the phrase at least one of A, B, and C should be construed to mean a logical (A or B or C), using a non-exclusive logical OR, and should not be construed as "at least one of A, at least one of B, and at least one of C."

[0135] In the accompanying drawings, the direction of the arrow, as shown by the arrow, generally indicates the flow of information (such as data or instructions) of interest to the illustration. For example, if element A and element B exchange various information, but the information transmitted from element A to element B is relevant to the illustration, the arrow may point from element A to element B. This unidirectional arrow does not imply that no other information is transmitted from element B to element A. Furthermore, for information transmitted from element A to element B, element B may send an information request to element A or receive an information confirmation.

[0136] In this application, including the definitions below, the term "circuit" may be used instead of the term "module" or the term "controller". The term "module" may refer to, be part of, or include an application-specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinational logic circuit; a field-programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system on a chip.

[0137] A module may include one or more interface circuits. In some examples, the interface circuits may include wired or wireless interfaces connected to a local area network (LAN), the Internet, a wide area network (WAN), or a combination thereof. The functionality of any given module of the present disclosure may be distributed across multiple modules connected via the interface circuits. For example, multiple modules may allow for load balancing. In further examples, a server (also known as a remote or cloud) module may perform some functions on behalf of a client module.

[0138] The term code, as used above, may encompass software, firmware, and / or microcode, and may refer to programs, routines, functions, classes, data structures, and / or objects. The term shared processor circuit includes a single processor circuit that executes some or all code from multiple modules. The term group processor circuit includes a processor circuit that, in conjunction with additional processor circuits, executes some or all code from one or more modules. Reference to multiple processor circuits includes multiple processor circuits on discrete dies, multiple processor circuits on a single die, multiple cores of a single processor circuit, multiple threads of a single processor circuit, or a combination of the foregoing. The term shared memory circuit includes a single memory circuit that stores some or all code from multiple modules. The term group memory circuit includes a memory circuit that, in conjunction with additional memory, stores some or all code from one or more modules.

[0139] The term memory circuit is a subset of the term computer-readable medium. As used herein, the term computer-readable medium does not include transient electronic or electromagnetic signals propagating through a medium (e.g., on a carrier wave); the term computer-readable medium may therefore be considered tangible and non-transient. Non-limiting examples of non-transient, tangible computer-readable media are non-volatile memory circuits (e.g., flash memory circuits, erasable programmable read-only memory circuits, or mask read-only memory circuits), volatile memory circuits (e.g., static random access memory circuits or dynamic random access memory circuits), magnetic storage media (e.g., analog or digital magnetic tape or hard drives), and optical storage media (e.g., CDs, DVDs, or Blu-ray discs).

[0140] A special-purpose computer can be created by configuring a general-purpose computer to perform one or more specific functions implemented as a computer program, and the apparatus and method described in this application can be partially or fully implemented by the special-purpose computer. The above-mentioned functional blocks, flow chart components and other elements serve as software instructions, which can be converted into a computer program through routine work by a technician or programmer.

[0141] The computer program includes processor-executable instructions stored on at least one non-transitory tangible computer-readable medium. The computer program may also include or rely on stored data. The computer program may include a basic input / output system (BIOS) that interacts with the hardware of the special-purpose computer, device drivers that interact with specific devices of the special-purpose computer, one or more operating systems, user applications, background services, background applications, and the like.

[0142] A computer program may include: (i) descriptive text to be parsed, such as HTML (Hypertext Markup Language), XML (Extensible Markup Language), or JSON (JavaScript Object Notation), (ii) assembly code, (iii) object code generated by a compiler from source code, (iv) source code executed by a translator, (v) source code compiled and executed by a just-in-time compiler, etc. By way of example only, the source code may be written using a syntax formed by languages ​​including C, C++, C#, Objective-C, Swift, Haskell, Go, SQL, R, Lisp, Java®, Fortran, Perl, Pascal, Curl, OCaml, Javascript®, HTML5 (Hypertext Markup Language Fifth Revision), Ada, ASP (Active Server Pages), PHP (PHP: Hypertext Preprocessor Language), Scala, Eiffel, Smalltalk, Erlang, Ruby, Flash®, Visual Basic®, Lua, MATLAB, SIMULINK, and Python®.

Claims

1. A climate control system comprising: a memory configured to store images acquired by the one or more image sensors; A compensation module is constructed to: estimating a clothing level of a first occupant in an interior cabin of the vehicle based on the image or receiving the clothing level from at least one of an edge computing device or a cloud-based network device; determining a first equivalent homogenizing temperature set point, i.e., a first EHT set point; Based on the clothing level and the first EHT set point, a first resultant EHT is determined, specifically: Calculate EHT compensation based on skin temperature and baseline EHT temperature at baseline clothing level; as well as determining the first synthetic EHT based on the EHT compensation value and the first EHT set point; The climate control system further comprises a climate control module, which is configured to: determining a first EHT error based on the first composite EHT and a cabin temperature set point; determining a control value based on the first EHT error; as well as A climate control parameter is set to control a temperature of a first area within the interior cabin based on the control value. 2 . The climate control system of claim 1 , further comprising the one or more image sensors. 3 . The climate control system of claim 1 , further comprising a transceiver configured to transmit the image to the edge computing device and receive the clothing level from the edge computing device.

4. The climate control system of claim 3 , further comprising the edge computing device, wherein the edge computing device includes a convolutional neural network configured to analyze the image and estimate the clothing level of the first occupant based on an analysis result provided by the convolutional neural network. 5 . The climate control system of claim 1 , further comprising a transceiver configured to transmit the image to the cloud-based network device and receive the clothing level from the cloud-based network device.

6. The climate control system of claim 1 , wherein: The EHT compensation value is calculated by the following formula: Where ΔT Iclo-EHT is the EHT compensation value, Iclo is the determined clothing level, Iclo0 is the baseline clothing level, Tskin is the skin temperature, and T EHT0 is the baseline EHT temperature at the baseline clothing level.

7. The climate control system of claim 1 , wherein: The compensation module is configured as estimating a clothing level of a second occupant in the interior cabin of the vehicle based on the image or receiving the clothing level of the second occupant from the at least one of the edge computing device or the cloud-based network device; determining a second EHT set point; as well as Based on the clothing level of the second occupant and the second EHT set point, a second resultant EHT is determined, specifically: calculating a second EHT compensation value based on the skin temperature and the baseline EHT temperature at the baseline clothing level; determining the second synthetic EHT based on the second EHT compensation value and the second EHT set point; The climate control module is configured to determining a second EHT error based on the second synthetic EHT and a second cabin temperature set point for a second zone; determining another control value based on the second EHT error; as well as A climate control parameter is set to control the temperature of the second area within the interior cabin based on the other control value. 8 . The climate control system of claim 7 , further comprising a transceiver configured to transmit the image to the edge computing device and receive the clothing level of the second occupant from the edge computing device. 9 . The climate control system of claim 7 , further comprising a transceiver configured to transmit the image to the cloud-based network device and receive the clothing level of the second occupant from the cloud-based network device. 10 . The climate control system of claim 1 , wherein the climate control module is configured to set the climate control parameter to adjust an opacity level of at least one of a sunroof or one or more vehicle windows.

11. A method of climate control, comprising: capturing images by one or more image sensors and storing them in a memory; estimating a clothing level of a first occupant in an interior cabin of the vehicle based on the image or receiving the clothing level from at least one of an edge computing device or a cloud-based network device; determining a first equivalent homogenizing temperature set point, i.e., a first EHT set point; Based on the clothing level and the first EHT set point, a first resultant EHT is determined, specifically: Calculate EHT compensation based on skin temperature and baseline EHT temperature at baseline clothing level; determining the first synthetic EHT based on the EHT compensation value and the first EHT set point; as well as determining a first EHT error based on the first composite EHT and a cabin temperature set point; determining a control value based on the first EHT error; as well as A climate control parameter is set to control a temperature of a first area within the interior cabin based on the control value.

12. The climate control method of claim 11, further comprising transmitting the image to the edge computing device and receiving the clothing level from the edge computing device. 13 . The climate control method of claim 12 , further comprising analyzing the image via a convolutional neural network, and estimating the clothing level of the first occupant based on analysis results provided by the convolutional neural network. 14 . The climate control method of claim 11 , further comprising transmitting the image to the cloud-based network device and receiving the clothing level from the cloud-based network device. 15 . The climate control method of claim 14 , further comprising analyzing the image via a convolutional neural network, and estimating the clothing level of the first occupant based on analysis results provided by the convolutional neural network.

16. The climate control method according to claim 11, wherein: The EHT compensation value is calculated by the following formula: Where ΔT Iclo-EHT is the EHT compensation value, Iclo is the determined clothing level, Iclo0 is the baseline clothing level, Tskin is the skin temperature, and T EHT0 is the baseline EHT temperature at the baseline clothing level.

17. The climate control method according to claim 11, further comprising: estimating a clothing level of a second occupant in the interior cabin of the vehicle based on the image or receiving the clothing level of the second occupant from the at least one of the edge computing device or the cloud-based network device; determining a second EHT set point; Based on the clothing level of the second occupant and the second EHT set point, a second resultant EHT is determined, specifically: calculating a second EHT compensation value based on the skin temperature and the baseline EHT temperature at the baseline clothing level; determining the second synthetic EHT based on the second EHT compensation value and the second EHT set point; determining a second EHT error based on the second composite EHT and a second cabin temperature set point for a second zone; determining another control value based on the second EHT error; as well as A climate control parameter is set to control the temperature of the second area within the interior cabin based on the other control value. 18 . The climate control method of claim 17 , further comprising transmitting the image to the edge computing device and receiving the clothing level of the second occupant from the edge computing device. 19 . The climate control method of claim 17 , further comprising transmitting the image to the cloud-based network device and receiving the clothing level of the second occupant from the cloud-based network device.

20. The climate control method of claim 11, further comprising setting the climate control parameter to adjust an opacity level of at least one of a sunroof or one or more vehicle windows.

Images